[dpdk-dev] [PATCH v2] bus/pci: check if 5-level paging is enabled when testing IOMMU address width

[Drocula]

The kernel version 4.14 released with the support of 5-level paging.
When PML5 enabled, user-space virtual addresses uses up to 56 bits.
see kernel's Documentation/x86/x86_64/mm.txt.

Signed-off-by: ZY Qiu <quze...@gmail.com>
---
 drivers/bus/pci/linux/pci.c | 33 ++++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/drivers/bus/pci/linux/pci.c b/drivers/bus/pci/linux/pci.c
index 04648ac..acc19df 100644
--- a/drivers/bus/pci/linux/pci.c
+++ b/drivers/bus/pci/linux/pci.c
@@ -4,6 +4,7 @@
 
 #include <string.h>
 #include <dirent.h>
+#include <sys/mman.h>
 
 #include <rte_log.h>
 #include <rte_bus.h>
@@ -552,16 +553,39 @@
 }
 
 #if defined(RTE_ARCH_X86)
+/*
+ * Try to detect whether the system uses 5-level page table.
+ */
+static bool
+system_uses_PML5(void)
+{
+#define X86_56_BIT_VA (0xfULL << 52)
+       void *page_4k;
+       page_4k = mmap((void *)X86_56_BIT_VA, 4096, PROT_READ | PROT_WRITE,
+               MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+
+       if (page_4k == MAP_FAILED)
+               return false;
+       munmap(page_4k, 4096);
+
+       if ((unsigned long long)page_4k & X86_56_BIT_VA)
+               return true;
+       return false;
+}
+
 static bool
 pci_one_device_iommu_support_va(struct rte_pci_device *dev)
 {
 #define VTD_CAP_MGAW_SHIFT     16
 #define VTD_CAP_MGAW_MASK      (0x3fULL << VTD_CAP_MGAW_SHIFT)
-#define X86_VA_WIDTH 47 /* From Documentation/x86/x86_64/mm.txt */
+/*  From Documentation/x86/x86_64/mm.txt */
+#define X86_VA_WIDTH_PML4 47
+#define X86_VA_WIDTH_PML5 56
+
        struct rte_pci_addr *addr = &dev->addr;
        char filename[PATH_MAX];
        FILE *fp;
-       uint64_t mgaw, vtd_cap_reg = 0;
+       uint64_t mgaw, vtd_cap_reg = 0, va_width = X86_VA_WIDTH_PML4;
 
        snprintf(filename, sizeof(filename),
                 "%s/" PCI_PRI_FMT "/iommu/intel-iommu/cap",
@@ -587,8 +611,11 @@
 
        fclose(fp);
 
+       if (system_uses_PML5())
+               va_width = X86_VA_WIDTH_PML5;
+
        mgaw = ((vtd_cap_reg & VTD_CAP_MGAW_MASK) >> VTD_CAP_MGAW_SHIFT) + 1;
-       if (mgaw < X86_VA_WIDTH)
+       if (mgaw < va_width)
                return false;
 
        return true;
-- 
1.8.3.1